Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation.
Jiaxu ZhuWeinan TongYaoxun XuChanghe SongZhiyong WuZhao YouDan SuDong YuHelen M. MengPublished in: CoRR (2023)
Keyphrases
- end to end
- speech recognition
- domain adaptation
- speech recognition systems
- speaker independent
- hidden markov models
- speech recognizers
- feature representation
- pattern recognition
- speech recognizer
- automatic speech recognition
- language model
- acoustic models
- information retrieval
- speech synthesis
- multiple sources
- speech signal
- semi supervised
- semi supervised learning
- cross domain
- labeled data
- text mining
- speaker identification
- transfer learning
- web documents
- bayesian networks
- document classification
- keywords
- text documents
- test data
- machine learning
- sentiment classification
- text to speech
- data mining